{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014771048744460856,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014771048744460858,
      "grad_norm": 98.73104858398438,
      "learning_rate": 2e-05,
      "loss": 34.9954,
      "step": 1
    },
    {
      "epoch": 0.0014771048744460858,
      "eval_loss": 9.048495292663574,
      "eval_runtime": 44.0686,
      "eval_samples_per_second": 6.49,
      "eval_steps_per_second": 3.245,
      "step": 1
    },
    {
      "epoch": 0.0029542097488921715,
      "grad_norm": 94.2271957397461,
      "learning_rate": 4e-05,
      "loss": 37.247,
      "step": 2
    },
    {
      "epoch": 0.004431314623338257,
      "grad_norm": 113.92647552490234,
      "learning_rate": 6e-05,
      "loss": 36.5254,
      "step": 3
    },
    {
      "epoch": 0.004431314623338257,
      "eval_loss": 8.65430736541748,
      "eval_runtime": 43.419,
      "eval_samples_per_second": 6.587,
      "eval_steps_per_second": 3.293,
      "step": 3
    },
    {
      "epoch": 0.005908419497784343,
      "grad_norm": 111.82482147216797,
      "learning_rate": 8e-05,
      "loss": 37.1602,
      "step": 4
    },
    {
      "epoch": 0.007385524372230428,
      "grad_norm": 92.45610809326172,
      "learning_rate": 0.0001,
      "loss": 35.1891,
      "step": 5
    },
    {
      "epoch": 0.008862629246676515,
      "grad_norm": 91.56773376464844,
      "learning_rate": 0.00012,
      "loss": 32.6143,
      "step": 6
    },
    {
      "epoch": 0.008862629246676515,
      "eval_loss": 7.128663063049316,
      "eval_runtime": 43.4757,
      "eval_samples_per_second": 6.578,
      "eval_steps_per_second": 3.289,
      "step": 6
    },
    {
      "epoch": 0.0103397341211226,
      "grad_norm": 88.56855010986328,
      "learning_rate": 0.00014,
      "loss": 29.8127,
      "step": 7
    },
    {
      "epoch": 0.011816838995568686,
      "grad_norm": 82.56781005859375,
      "learning_rate": 0.00016,
      "loss": 25.4548,
      "step": 8
    },
    {
      "epoch": 0.013293943870014771,
      "grad_norm": 76.79576110839844,
      "learning_rate": 0.00018,
      "loss": 22.9964,
      "step": 9
    },
    {
      "epoch": 0.013293943870014771,
      "eval_loss": 5.095368385314941,
      "eval_runtime": 43.5257,
      "eval_samples_per_second": 6.571,
      "eval_steps_per_second": 3.285,
      "step": 9
    },
    {
      "epoch": 0.014771048744460856,
      "grad_norm": 70.41092681884766,
      "learning_rate": 0.0002,
      "loss": 22.0738,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 172445285744640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}